add dockerfile

Dockerfile

@@ -1,6 +1,8 @@
 FROM pytorch/pytorch:1.13.1-cuda11.6-cudnn8-runtime
 COPY . .
 RUN pip3  install -r requirements.txt
-RUN python3 pull_model.py
+ENV model_path="/model"
+
 EXPOSE 7860
-CMD [ "python","web_demo.py" ]
+
+CMD [ "python","web_demo./py" ]

README.md

@@ -34,7 +34,11 @@ ChatGLM-6B 使用了和 ChatGPT 相似的技术，针对中文问答和对话进
 ### 环境安装
 
 使用 pip 安装依赖：`pip install -r requirements.txt`，其中 `transformers` 库版本推荐为 `4.26.1`，但理论上不低于 `4.23.1` 即可。
-
+### docker镜像部署
+```bash
+docker build -t chatglm .
+docker run -v /the/model/path:/model chatglm
+```
 ### 代码调用 
 
 可以通过如下代码调用 ChatGLM-6B 模型来生成对话：

pull_model.py

@@ -1,2 +0,0 @@
-from transformers import  AutoModel
-model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()

web_demo.py

@@ -1,10 +1,14 @@
 from transformers import AutoModel, AutoTokenizer
 import gradio as gr
-
-tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
-model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
+import os
+modelPath = os.getenv('model_path')
+modelPath = modelPath if  modelPath!="" else "THUDM/chatglm-6b" 
+tokenizer = AutoTokenizer.from_pretrained(modelPath, trust_remote_code=True)
+model = AutoModel.from_pretrained(modelPath, trust_remote_code=True).half().cuda()
 model = model.eval()
 
+
+
 MAX_TURNS = 20
 MAX_BOXES = MAX_TURNS * 2
 
@@ -42,4 +46,4 @@ with gr.Blocks() as demo:
             temperature = gr.Slider(0, 1, value=0.95, step=0.01, label="Temperature", interactive=True)
             button = gr.Button("Generate")
     button.click(predict, [txt, max_length, top_p, temperature, state], [state] + text_boxes)
-demo.queue().launch(share=False, inbrowser=True)
+demo.queue().launch(share=False, inbrowser=True,server_name="0.0.0.0")